Cambium runs on your own machine — the client starts it, so there is no endpoint to ping. 75 installs a week from pypi. Last commit 6 Aug 2026.
Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org.
We read the source, 22 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
p = subprocess.run(
path = os.path.join(cfg["context_dir"], fname)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add cambium -- uvx cambium-mcp
{
"mcpServers": {
"cambium": {
"args": [
"cambium-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.cambium]
command = "uvx"
args = ["cambium-mcp"]
{
"mcpServers": {
"cambium": {
"args": [
"cambium-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"cambium": {
"args": [
"cambium-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
CAMBIUM_REPO (Absolute path to the project git clone cambium reads/writes. Defaults to the current repo (cwd git root) when unset.), CAMBIUM_AGENT_ID (Your unique agent id, attributed to captures/endorsements/promotions.), CAMBIUM_ORG_REPO (Path to the org knowledge repo clone (org scope). Omit to keep promotions at team scope.).
The author declared them in the registry entry; get the values from the project itself.
Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.
Persistent memory for AI agents. Store, recall, and share knowledge across sessions.
Private Agent memory and governed shared knowledge.
Local-first knowledge engine for AI agents: memory, graph, and recall over MCP.
Personal knowledge graph every MCP client reads from and writes to. Portable across agents.
Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall
AI-native project management + agent memory: tasks, sprints, risk, burnout, knowledge search.
Project memory across sessions for AI agents. A queryable decision log in the repo.
Answers built from our own checks of this server.